Merge pull request #5483 from MicrosoftDocs/main

6/11/2025 PM Publish

Author: Taojunshen

articles/ai-foundry/concepts/fine-tuning-overview.md

@@ -29,8 +29,6 @@ Consider fine-tuning GenAI models to:
 
 [Azure AI Foundry](https://ai.azure.com/?cid=learnDocs) offers several models across model providers enabling you to get access to the latest and greatest in the market. [View this list for more details](#supported-models-for-fine-tuning). 
 
-:::image type="content" source="../media/concepts/model-catalog-fine-tuning.png" alt-text="Screenshot of Azure AI Foundry model catalog and filtering by Fine-tuning tasks." lightbox="../media/concepts/model-catalog-fine-tuning.png":::
-
 ## Getting started with fine-tuning
 
 When starting out on your generative AI journey, we recommend you begin with prompt engineering and RAG to familiarize yourself with base models and its capabilities. 

articles/ai-foundry/media/concepts/model-catalog-fine-tuning.png

@@ -9,7 +9,7 @@ ms.custom:
   - ignite-2023
   - ignite-2024
 ms.topic: how-to
-ms.date: 04/02/2025
+ms.date: 06/11/2025
 ---
 
 # Attach an Azure AI services resource to a skillset in Azure AI Search
@@ -22,7 +22,6 @@ An Azure AI services multi-service resource provides a collection of Azure AI se
 
 + [Azure AI Vision](/azure/ai-services/computer-vision/overview) for image analysis, optical character recognition (OCR), and multimodal embeddings
 + [Azure AI Language](/azure/ai-services/language-service/overview) for language detection, entity recognition, sentiment analysis, and key phrase extraction
-+ [Azure AI Speech](/azure/ai-services/speech-service/overview) for speech to text and text to speech
 + [Azure AI Translator](/azure/ai-services/translator/translator-overview) for machine text translation
 
 Exceptions to billing through the multi-service resource include [AzureOpenAIEmbedding](cognitive-search-skill-azure-openai-embedding.md) or the [AML skill](cognitive-search-aml-skill.md) billing. Azure AI Search doesn't internally host models from Azure OpenAI or the Azure AI Foundry model catalog. Usage for AML and Azure OpenAI skills and vectorizers are through [Azure OpenAI Standard pricing](https://azure.microsoft.com/pricing/details/cognitive-services/openai-service/#pricing) and [Azure Machine Learning Standard pricing](https://azure.microsoft.com/pricing/details/machine-learning/), respectively. A few other skills, such as Text Split and Text Merge, aren't billable.

articles/ai-services/openai/concepts/fine-tuning-considerations.md

@@ -11,7 +11,7 @@ ms.custom:
   - references_regions
   - build-2024
 ms.topic: how-to
-ms.date: 04/28/2025
+ms.date: 06/11/2025
 ---
 
 # Create an Azure AI Search service in the Azure portal
@@ -116,22 +116,11 @@ In most cases, choose a region near you, unless any of the following apply:
 
 1. Do you have business continuity and disaster recovery (BCDR) requirements? Create two or more search services in [regional pairs](/azure/reliability/cross-region-replication-azure#azure-paired-regions) within [availability zones](search-reliability.md#availability-zones). For example, if you're operating in North America, you might choose East US and West US, or North Central US and South Central US, for each search service.
 
-1. Do you need [AI enrichment](cognitive-search-concept-intro.md), [integrated data chunking and vectorization](vector-search-integrated-vectorization.md), or [multimodal image search](search-get-started-portal-image-search.md)? Azure AI Search, Azure OpenAI, and Azure AI services multi-service must coexist in the same region.
+1. Do you need [AI enrichment](cognitive-search-concept-intro.md), [integrated data chunking and vectorization](vector-search-integrated-vectorization.md), or [multimodal search](multimodal-search-overview.md)? For [billing purposes](cognitive-search-attach-cognitive-services.md), Azure AI Search and Azure AI services multi-service must coexist in the same region.
 
-   + Start with [Azure OpenAI regions](/azure/ai-services/openai/concepts/models#model-summary-table-and-region-availability) because they have the most variability. Azure OpenAI provides embedding models and chat models for RAG and integrated vectorization.
+   + Check [Azure AI Search regions](search-region-support.md#azure-public-regions). If you're using OCR, entity recognition, or other skills backed by Azure AI, the **AI enrichment** column indicates whether Azure AI Search and Azure AI services multi-service are in the same region.
 
-   + Check [Azure AI Search regions](search-region-support.md#azure-public-regions) for a match to your Azure OpenAI region. If you're using OCR, entity recognition, or other skills backed by Azure AI, the **AI enrichment** column indicates whether Azure AI services multi-service and Azure AI Search are in the same region.
-
-   + Check [multimodal embedding regions](/azure/ai-services/computer-vision/overview-image-analysis#region-availability) for multimodal APIs and image search. This API is accessed through an Azure AI services multi-service account, but in general, it's available in fewer regions than Azure AI services multi-service.
-
-### Regions with the most overlap
-
-Currently, the following regions offer cross-regional availability for Azure AI Search, Azure OpenAI, and Azure AI Vision multimodal:
-
-+ Americas: West US, East US
-+ Europe: Switzerland North, Sweden Central
-
-This list isn't definitive, and depending on your tier, you might have more choices. Region status can also change quickly, so confirm your region choice before you create your search service.
+   + Check [Azure AI Vision regions](/azure/ai-services/computer-vision/overview-image-analysis#region-availability) for multimodal APIs that enable text and image vectorization. These APIs are powered by Azure AI Vision and accessed through an Azure AI services multi-service resource. However, they're generally available in fewer regions than the multi-service resource itself.
 
 ## Choose a tier
 

articles/search/cognitive-search-attach-cognitive-services.md

@@ -6,7 +6,7 @@ author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: quickstart
-ms.date: 06/04/2025
+ms.date: 06/11/2025
 ms.custom:
   - references_regions
 ---
@@ -42,7 +42,7 @@ For content extraction, you can choose either default extraction via Azure AI Se
 | Default extraction | Extracts location metadata from PDF images only. Doesn't require another Azure AI resource. |
 | Enhanced extraction | Extracts location metadata from text and images for multiple document types. Requires an [Azure AI services multi-service resource](/azure/ai-services/multi-service-resource#azure-ai-multi-services-resource-for-azure-ai-search-skills) <sup>1</sup> in a [supported region](cognitive-search-skill-document-intelligence-layout.md#supported-regions). |
 
-<sup>1</sup> For billing purposes, you must [attach your multi-service resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
+<sup>1</sup> For billing purposes, you must [attach your Azure AI multi-service resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
 
 ### Supported embedding methods
 
@@ -57,7 +57,7 @@ For content embedding, you can choose either image verbalization (followed by te
 
 <sup>2</sup> Azure OpenAI resources (with access to embedding models) that were created in the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) aren't supported. You must create an Azure OpenAI resource in the Azure portal.
 
-<sup>3</sup> For billing purposes, you must [attach your multi-service resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
+<sup>3</sup> For billing purposes, you must [attach your Azure AI multi-service resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
 
 <sup>4</sup> `phi-4` is only available to Azure AI Foundry projects.
 
@@ -300,7 +300,7 @@ To use the skills for multimodal embeddings:
 
 1. For the kind, select your model provider: **AI Foundry Hub catalog models** or **AI Vision vectorization**.
 
-   <!-- If it's unavailable, make sure your Azure AI Search service and Azure AI multi-service account are both in a region that [supports the AI Vision multimodal APIs](/azure/ai-services/computer-vision/how-to/image-retrieval). -->
+   If Azure AI Vision is unavailable, make sure your search service and multi-service resource are both in a [region that supports the Azure AI Vision multimodal APIs](/azure/ai-services/computer-vision/how-to/image-retrieval).
 
 1. Specify your Azure subscription, resource, and embedding model deployment.
 

articles/search/search-create-service-portal.md

@@ -9,7 +9,7 @@ ms.custom:
   - build-2024
   - ignite-2024
 ms.topic: quickstart
-ms.date: 06/04/2025
+ms.date: 06/11/2025
 ---
 
 # Quickstart: Vectorize text in the Azure portal
@@ -42,7 +42,7 @@ The **Import and vectorize data wizard** [supports a wide range of Azure data so
 
 ### Supported embedding models
 
-For integrated vectorization, you must use one of the following embedding models on an Azure AI platform in the [same region as Azure AI Search](search-create-service-portal.md#regions-with-the-most-overlap). Deployment instructions are provided in a [later section](#prepare-embedding-model).
+For integrated vectorization, you must use one of the following embedding models on an Azure AI platform. Deployment instructions are provided in a [later section](#prepare-embedding-model).
 
 | Provider | Supported models |
 |--|--|
@@ -54,7 +54,7 @@ For integrated vectorization, you must use one of the following embedding models
 
 <sup>2</sup> Azure OpenAI resources (with access to embedding models) that were created in the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) aren't supported. Only Azure OpenAI resources created in the Azure portal are compatible with the [Azure OpenAI Embedding skill](cognitive-search-skill-azure-openai-embedding.md).
 
-<sup>3</sup> For billing purposes, you must [attach your multi-service resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
+<sup>3</sup> For billing purposes, you must [attach your Azure AI multi-service resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
 
 <sup>4</sup> The Azure AI Vision multimodal embedding model is available in [select regions](/azure/ai-services/computer-vision/overview-image-analysis#region-availability).
 
@@ -375,7 +375,7 @@ In this step, you specify an embedding model to vectorize chunked data. Chunking
 
    + Azure AI Foundry model catalog
 
-   + An Azure AI Vision multimodal resource in the same region as Azure AI Search. If there's no [Azure AI services multi-service account](/azure/ai-services/multi-service-resource#azure-ai-multi-services-resource-for-azure-ai-search-skills) in the same region, this option isn't available.
+   + Azure AI Vision (via an [Azure AI services multi-service resource](/azure/ai-services/multi-service-resource#azure-ai-multi-services-resource-for-azure-ai-search-skills) in the same region as Azure AI Search)
 
 1. Specify the Azure subscription.
 
@@ -385,11 +385,11 @@ In this step, you specify an embedding model to vectorize chunked data. Chunking
 
    + For AI Foundry model catalog, select the model you deployed in [Prepare embedding model](#prepare-embedding-model).
 
-   + For AI Vision multimodal embeddings, select your multi-service account.
+   + For AI Vision multimodal embeddings, select your multi-service resource.
 
 1. For the authentication type, select **System assigned identity**.
 
-   + The identity should have a **Cognitive Services User** role on the Azure AI services multi-services account.
+   + The identity should have a **Cognitive Services User** role on the Azure AI services multi-service resource.
 
 1. Select the checkbox that acknowledges the billing effects of using these resources.
 

articles/search/search-get-started-portal-image-search.md

@@ -8,7 +8,7 @@ ms.service: azure-ai-search
 ms.custom:
   - ignite-2024
 ms.topic: quickstart
-ms.date: 03/04/2025
+ms.date: 06/11/2025
 ---
 
 # Quickstart: Generative search (RAG) using grounding data from Azure AI Search
@@ -24,14 +24,11 @@ In this quickstart, you send queries to a chat completion model for a conversati
   - [Deploy the chat completion model](/azure/ai-foundry/how-to/deploy-models-openai) in Azure AI Foundry or [use another approach](/azure/ai-services/openai/how-to/working-with-models).
 
 - An [Azure AI Search resource](search-create-service-portal.md).
-  - Use the same region as your Azure OpenAI resource.
   - We recommend using the Basic tier or higher.
   - [Enable semantic ranking](semantic-how-to-enable-disable.md).
 
 - [Visual Studio Code](https://code.visualstudio.com/download) with the [Python extension](https://marketplace.visualstudio.com/items?itemName=ms-python.python) and the [Jupyter package](https://pypi.org/project/jupyter/). For more information, see [Python in Visual Studio Code](https://code.visualstudio.com/docs/languages/python).
 
-To meet the same-region requirement, start by reviewing the [regions for the chat model](/azure/ai-services/openai/concepts/models#model-summary-table-and-region-availability) you want to use. After you identify a region, confirm that Azure AI Search is available in the [same region](search-region-support.md#azure-public-regions).
-
 ## Download file
 
 [Download a Jupyter notebook](https://github.com/Azure-Samples/azure-search-python-samples/tree/main/Quickstart-RAG) from GitHub to send the requests in this quickstart. For more information, see [Downloading files from GitHub](https://docs.github.com/get-started/start-your-journey/downloading-files-from-github).

articles/search/search-get-started-portal-import-vectors.md

@@ -7,7 +7,7 @@ author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: how-to
-ms.date: 04/29/2025
+ms.date: 06/11/2025
 ---
 
 # Set up integrated vectorization in Azure AI Search using REST
@@ -42,7 +42,7 @@ Integrated vectorization works with [all supported data sources](search-indexer-
 
 ### Supported embedding models
 
-For integrated vectorization, you must use one of the following embedding models on an Azure AI platform in the [same region as Azure AI Search](search-create-service-portal.md#regions-with-the-most-overlap). Deployment instructions are provided in a [later section](#prepare-your-embedding-model).
+For integrated vectorization, you must use one of the following embedding models on an Azure AI platform. Deployment instructions are provided in a [later section](#prepare-your-embedding-model).
 
 | Provider | Supported models |
 |--|--|
@@ -52,7 +52,7 @@ For integrated vectorization, you must use one of the following embedding models
 
 <sup>1</sup> The endpoint of your Azure OpenAI resource must have a [custom subdomain](/azure/ai-services/cognitive-services-custom-subdomains), such as `https://my-unique-name.openai.azure.com`. If you created your resource in the [Azure portal](https://portal.azure.com/), this subdomain was automatically generated during resource setup.
 
-<sup>2</sup> Azure OpenAI resources (with access to embedding models) that were created in the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) aren't supported. Only Azure OpenAI resources created in the Azure portal are compatible with the [Azure OpenAI Embedding skill](cognitive-search-skill-azure-openai-embedding.md) integration.
+<sup>2</sup> Azure OpenAI resources (with access to embedding models) that were created in the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs) aren't supported. Only Azure OpenAI resources created in the Azure portal are compatible with the [Azure OpenAI Embedding skill](cognitive-search-skill-azure-openai-embedding.md).
 
 <sup>3</sup> For billing purposes, you must [attach your Azure AI multi-service resource](cognitive-search-attach-cognitive-services.md) to the skillset in your Azure AI Search service. Unless you use a [keyless connection (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) to create the skillset, both resources must be in the same region.
 

articles/search/search-get-started-rag.md

@@ -6,7 +6,7 @@ author: haileytap
 ms.author: haileytapia
 ms.service: azure-ai-search
 ms.topic: how-to
-ms.date: 05/08/2025
+ms.date: 06/11/2025
 ms.custom:
   - references_regions
   - ignite-2024
@@ -42,9 +42,9 @@ For illustration purposes, this article uses the [sample health plan PDFs](https
 
 + A skillset with these two skills:
 
-  + [Document Layout skill](cognitive-search-skill-document-intelligence-layout.md) that splits documents based on paragraph boundaries. This skill has region requirements. An Azure AI multi-service resource must be in the same region as Azure AI Search with AI Enrichment.
+  + [Document Layout skill](cognitive-search-skill-document-intelligence-layout.md) that splits documents based on paragraph boundaries. This skill has region requirements. An Azure AI multi-service resource must be in the same region as Azure AI Search with AI enrichment.
 
-  + [Azure OpenAI Embedding skill](cognitive-search-skill-azure-openai-embedding.md) that generates vector embeddings. This skill also has region requirements. The model must be in the same region as Azure AI Search.
+  + [Azure OpenAI Embedding skill](cognitive-search-skill-azure-openai-embedding.md) that generates vector embeddings. This skill *doesn't* have region requirements.
 
 ## Prepare data files